© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119890
    Prev
    Next
    INDEX
    Explanations

    foreign words, brands, and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     влияет
    -0.06
     erwähnt
    -0.06
     effic
    -0.06
     फैली
    -0.06
    ódio
    -0.06
     separated
    -0.06
     मार्ग
    -0.06
     aggress
    -0.06
    Subview
    -0.06
     resigned
    -0.06
    POSITIVE LOGITS
     bunda
    0.06
    నే
    0.06
     આપણા
    0.06
     iconic
    0.06
    而且
    0.05
     moreover
    0.05
     yn
    0.05
     ImageIcon
    0.05
     insbesondere
    0.05
    \@
    0.05
    Activations Density 0.046%

    No Known Activations